{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T07:26:16Z","timestamp":1740122776350,"version":"3.37.3"},"reference-count":38,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2018,8,28]],"date-time":"2018-08-28T00:00:00Z","timestamp":1535414400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Speech Technol"],"published-print":{"date-parts":[[2019,9]]},"DOI":"10.1007\/s10772-018-9549-y","type":"journal-article","created":{"date-parts":[[2018,8,28]],"date-time":"2018-08-28T12:09:45Z","timestamp":1535458185000},"page":"483-496","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Emotional speech analysis using harmonic plus noise model and Gaussian mixture model"],"prefix":"10.1007","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7017-1989","authenticated-orcid":false,"given":"Jang Bahadur","family":"Singh","sequence":"first","affiliation":[]},{"given":"Parveen Kumar","family":"Lehana","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,8,28]]},"reference":[{"key":"9549_CR1","volume-title":"Akaike\u2019s information criterion. International encyclopedia of statistical science","author":"H Akaike","year":"2011","unstructured":"Akaike, H. (2011). Akaike\u2019s information criterion. International encyclopedia of statistical science. Berlin: Springer."},{"key":"9549_CR2","unstructured":"Ali, F. B., & Djaziri-Larbi, S. (2017). A long term harmonic plus noise model for narrow-band speech coding at very low bit-rates. In Telecommunications and Signal Processing, 40th International Conference, pp. 372\u2013376."},{"issue":"2","key":"9549_CR3","doi-asserted-by":"publisher","first-page":"155","DOI":"10.1007\/s10462-012-9368-5","volume":"43","author":"CN Anagnostopoulos","year":"2015","unstructured":"Anagnostopoulos, C. N., Iliou, T., & Giannoukos, I. (2015). Features and classifiers for emotion recognition from speech: A survey from 2000 to 2011. Artificial Intelligence Review., 43(2), 155\u2013177.","journal-title":"Artificial Intelligence Review."},{"key":"9549_CR4","doi-asserted-by":"crossref","unstructured":"Bandoin, G., & Stylianou, Y. (1996). On the transformation of the speech spectrum for voice conversion. In Proceeding of Fourth International Conference on Spoken Language Processing ICSLP \u201996.","DOI":"10.1109\/ICSLP.1996.607877"},{"key":"9549_CR5","doi-asserted-by":"crossref","unstructured":"Bhaykar, M., Yadav, J., & Rao, K. S. (2013). Speaker dependent, speaker independent and cross language emotion recognition from speech using GMM and HMM. In Communications, National Conference, pp. 1\u20135.","DOI":"10.1109\/NCC.2013.6487998"},{"key":"9549_CR6","doi-asserted-by":"crossref","unstructured":"Burkhardt, F., Paeschke, A., Rolfes, M., Sendlmeier, W. F., & Weiss, B. (2005). A database of German emotional speech. In Ninth European Conference on Speech Communication and Technology.","DOI":"10.21437\/Interspeech.2005-446"},{"issue":"20","key":"9549_CR7","doi-asserted-by":"publisher","first-page":"6","DOI":"10.5120\/431-636","volume":"1","author":"Y Chavhan","year":"2010","unstructured":"Chavhan, Y., Dhore, M. L., & Yesaware, P. (2010). Speech emotion recognition using support vector machine. International Journal of Computer Applications, 1(20), 6\u20139.","journal-title":"International Journal of Computer Applications"},{"issue":"10","key":"9549_CR9","doi-asserted-by":"publisher","first-page":"2085","DOI":"10.1109\/TASL.2013.2266772","volume":"21","author":"G Degottex","year":"2013","unstructured":"Degottex, G., & Stylianou, Y. (2013). Analysis and synthesis of speech using an adaptive full-band harmonic model. IEEE Transactions on Audio, Speech, and Language Processing, 21(10), 2085\u20132095.","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"issue":"2","key":"9549_CR10","doi-asserted-by":"publisher","first-page":"184","DOI":"10.1109\/JSTSP.2013.2283471","volume":"8","author":"D Erro","year":"2014","unstructured":"Erro, D., Sainz, I., Navas, E., & Hernaez, I. (2014). Harmonics plus noise model based vocoder for statistical parametric speech synthesis. IEEE Journal of Selected Topics in Signal Processing, 8(2), 184\u2013194.","journal-title":"IEEE Journal of Selected Topics in Signal Processing"},{"key":"9549_CR11","unstructured":"Eslava, D. E., & Bilbao, A. M. (2008). Intra-lingual and cross-lingual voice conversion using harmonic plus stochastic models. Barcelona, Spain: PhD Thesis, Universitat Politechnica de Catalunya."},{"issue":"6","key":"9549_CR12","first-page":"1056","volume":"22","author":"MJ Gangeh","year":"2014","unstructured":"Gangeh, M. J., Fewzee, P., Ghodsi, A., Kamel, M. S., & Karray, F. (2014). Multiview supervised dictionary learning in speech emotion recognition. IEEE\/ACM Transactions on Audio, Speech, and Language Processing Institute of Electrical and Electronics Engineers (IEEE), 22(6), 1056\u20131068.","journal-title":"IEEE\/ACM Transactions on Audio, Speech, and Language Processing Institute of Electrical and Electronics Engineers (IEEE)"},{"key":"9549_CR13","doi-asserted-by":"crossref","unstructured":"Han, K., Yu, D., & Tashev, I. (2014). Speech emotion recognition using deep neural network and extreme learning machine. In Fifteenth Annual Conference of the International Speech Communication Association.","DOI":"10.21437\/Interspeech.2014-57"},{"issue":"1","key":"9549_CR14","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1007\/s10772-016-9386-9","volume":"20","author":"A Haque","year":"2017","unstructured":"Haque, A., & Rao, K. S. (2017). Modification of energy spectra, epoch parameters and prosody for emotion conversion in speech. International Journal of Speech Technology, 20(1), 15\u201325.","journal-title":"International Journal of Speech Technology"},{"key":"9549_CR15","unstructured":"Hemptinne, C. (2006). Integration of the harmonic plus noise model into the hidden Markov model-based speech synthesis system. Master thesis."},{"key":"9549_CR18","doi-asserted-by":"crossref","unstructured":"Kafentzis, G. P., Rosec, O., & Stylianou, Y. (2014a). Robust full-band adaptive Sinusoidal analysis and synthesis of speech. In International Conference on Acoustics, Speech, and Signal Processing, pp. 6260\u20136264.","DOI":"10.1109\/ICASSP.2014.6854808"},{"key":"9549_CR17","doi-asserted-by":"crossref","unstructured":"Kafentzis, G. P., Yakoumaki, T., Mouchtaris, A., & Stylianou, Y. (2014b). Analysis of emotional speech using an adaptive sinusoidal model. In European Signal Processing Conference, 2014 Proceedings of the 22nd European, pp. 1492\u20131496.","DOI":"10.21437\/Interspeech.2014-336"},{"issue":"3","key":"9549_CR19","doi-asserted-by":"publisher","first-page":"1306","DOI":"10.3906\/elk-1312-196","volume":"24","author":"S Karimi","year":"2016","unstructured":"Karimi, S., & Sedaaghi, M. H. (2016). How to categorize emotional speech signals with respect to the speaker\u2019s degree of emotional intensity. Turkish Journal of Electrical Engineering & Computer Sciences, 24(3), 1306\u20131324.","journal-title":"Turkish Journal of Electrical Engineering & Computer Sciences"},{"key":"9549_CR20","doi-asserted-by":"crossref","unstructured":"Khanna, P., & Kumar, M. S. (2011). Application of vector quantization in emotion recognition from human speech. In International Conference on Information Intelligence, Systems, Technology and Management, pp. 118\u2013125.","DOI":"10.1007\/978-3-642-19423-8_13"},{"key":"9549_CR21","doi-asserted-by":"crossref","unstructured":"Kwon, O. W., Chan, K., Hao, J., & Lee, T. W. (2003). Emotion recognition by speech signals. In Eighth European Conference on Speech Communication and Technology.","DOI":"10.21437\/Eurospeech.2003-80"},{"key":"9549_CR22","unstructured":"Lehana, P. K., & Pandey, P. C. (2004). Harmonic plus noise model based speech synthesis in Hindi and pitch modification. In Proceedings of the 16th International Congress on Acoustics, pp. 3333\u20133336."},{"issue":"4","key":"9549_CR23","doi-asserted-by":"publisher","first-page":"e0122731","DOI":"10.1371\/journal.pone.0122731","volume":"10","author":"R Li","year":"2015","unstructured":"Li, R., Perneczky, R., Yakushev, I., F\u00f6rster, S., Kurz, A., & Drzezga, A. (2015). Gaussian mixture models and model selection for [18F] fluorodeoxyglucose positron emission tomography classification in Alzheimer\u2019s disease. PLoS ONE, 10(4), e0122731.","journal-title":"PLoS ONE"},{"key":"9549_CR24","doi-asserted-by":"crossref","unstructured":"Mao, X., Chen, L., & Fu, L., (2009). Multi-level speech emotion recognition based on HMM and ANN. In 2009 World Congress on Computer Science and Information Engineering, Los Angeles, CA, pp. 225\u2013229.","DOI":"10.1109\/CSIE.2009.113"},{"issue":"6","key":"9549_CR25","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1109\/79.543975","volume":"13","author":"TK Moon","year":"1996","unstructured":"Moon, T. K. (1996). The expectation-maximization algorithm. IEEE Signal Processing Magazine, 13(6), 47\u201360.","journal-title":"IEEE Signal Processing Magazine"},{"issue":"4","key":"9549_CR26","doi-asserted-by":"publisher","first-page":"603","DOI":"10.1016\/S0167-6393(03)00099-2","volume":"41","author":"TL Nwe","year":"2003","unstructured":"Nwe, T. L., Foo, S. W., & De Silva, L. C. (2003). Speech emotion recognition using hidden Markov models. Speech Communication, 41(4), 603\u2013623.","journal-title":"Speech Communication"},{"key":"9549_CR29","unstructured":"Pantazis, Y., Rosec, O., & Stylianou, Y. (2008). On the estimation of the speech harmonic model. In ISCA Tutorial and Research Workshop (ITRW) on Speech Analysis and Processing for Knowledge Discovery."},{"issue":"2","key":"9549_CR27","doi-asserted-by":"publisher","first-page":"290","DOI":"10.1109\/TASL.2010.2047682","volume":"19","author":"Y Pantazis","year":"2011","unstructured":"Pantazis, Y., Rosec, O., & Stylianou, Y. (2011). Adaptive AM-FM signal decomposition with application to speech analysis. IEEE Transactions on Audio, Speech, and Language Processing, 19(2), 290\u2013300.","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"key":"9549_CR28","doi-asserted-by":"crossref","unstructured":"Pantazis, Y., & Stylianou, Y. (2008). Improving the modeling of the noise part in the harmonic plus noise model of speech. In Acoustics, Speech and Signal Processing, IEEE International Conference, pp. 4609\u20134612.","DOI":"10.1109\/ICASSP.2008.4518683"},{"issue":"3","key":"9549_CR30","doi-asserted-by":"publisher","first-page":"1467","DOI":"10.1007\/s11235-011-9624-z","volume":"52","author":"S Ramakrishnan","year":"2013","unstructured":"Ramakrishnan, S., & El Emary, I. M. (2013). Speech emotion recognition approaches in human computer interaction. Telecommunication Systems, 52(3), 1467\u20131478.","journal-title":"Telecommunication Systems"},{"issue":"3","key":"9549_CR31","doi-asserted-by":"publisher","first-page":"737","DOI":"10.1109\/TSA.2005.858071","volume":"14","author":"S Ramamohan","year":"2006","unstructured":"Ramamohan, S., & Dandapat, S. (2006). Sinusoidal model-based analysis and classification of stressed speech. IEEE Transactions on Audio, Speech, and Language Processing, 14(3), 737\u2013746.","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"key":"9549_CR32","doi-asserted-by":"publisher","first-page":"2056","DOI":"10.3906\/elk-1302-90","volume":"23","author":"A Shahzadi","year":"2015","unstructured":"Shahzadi, A., Ahmadyfard, A., Harimi, A., & Yaghmaie, K. (2015). Speech emotion recognition using nonlinear dynamics features. Turkish Journal of Electrical Engineering & Computer Sciences, 23, 2056\u20132073.","journal-title":"Turkish Journal of Electrical Engineering & Computer Sciences"},{"issue":"3","key":"9549_CR33","doi-asserted-by":"publisher","first-page":"659","DOI":"10.1007\/s10772-017-9437-x","volume":"20","author":"R Singh","year":"2017","unstructured":"Singh, R., Kumar, A., & Lehana, P. K. (2017). Effect of bandwidth modifications on the quality of speech imitated by Alexandrine and Indian Ringneck parrots. International Journal of Speech Technology, 20(3), 659\u2013672.","journal-title":"International Journal of Speech Technology"},{"issue":"1","key":"9549_CR34","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1109\/89.890068","volume":"9","author":"Y Stylianou","year":"2001","unstructured":"Stylianou, Y. (2001). Applying the harmonic plus noise model in concatenative speech synthesis. IEEE Transactions on Speech and Audio Processing, 9(1), 21\u201329.","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"key":"9549_CR35","doi-asserted-by":"crossref","unstructured":"Stylianou, Y., & Cappe, O. (1998). A system for voice conversion based on probabilistic classification and a harmonic plus noise model. In Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP \u201998 (Cat No98CH36181).","DOI":"10.1109\/ICASSP.1998.674422"},{"issue":"4","key":"9549_CR36","doi-asserted-by":"publisher","first-page":"1145","DOI":"10.1109\/TASL.2006.876113","volume":"14","author":"J Tao","year":"2006","unstructured":"Tao, J., Kang, Y., & Li, A. (2006). Prosody conversion from neutral speech to emotional speech. IEEE Transactions on Audio, Speech and Language Processing, 14(4), 1145\u20131154.","journal-title":"IEEE Transactions on Audio, Speech and Language Processing"},{"issue":"2","key":"9549_CR37","doi-asserted-by":"publisher","first-page":"144","DOI":"10.1016\/j.specom.2007.01.001","volume":"49","author":"KP Truong","year":"2007","unstructured":"Truong, K. P., & van Leeuwen, D. A. (2007). Automatic discrimination between laughter and speech. Speech Communication, 49(2), 144\u2013158.","journal-title":"Speech Communication"},{"key":"9549_CR38","unstructured":"Ververidis, D., & Kotropoulos, C. (2004). Automatic speech classification to five emotional states based on gender information. In European Signal Processing Conference, pp. 341\u2013344."},{"key":"9549_CR39","unstructured":"Vogt, T., & Andr\u00e9, E. (2006). Improving automatic emotion recognition from speech via gender differentiation. In Proceedings of the Language Resources and Evaluation Conference, Genoa."},{"key":"9549_CR40","doi-asserted-by":"crossref","unstructured":"Yakoumaki, T., Kafentzis, G. P., & Stylianou, Y. (2014). Emotional speech classification using adaptive sinusoidal modelling. In Fifteenth Annual Conference of the International Speech Communication Association.","DOI":"10.21437\/Interspeech.2014-336"}],"container-title":["International Journal of Speech Technology"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-018-9549-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10772-018-9549-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-018-9549-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,30]],"date-time":"2022-08-30T17:38:51Z","timestamp":1661881131000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10772-018-9549-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,8,28]]},"references-count":38,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2019,9]]}},"alternative-id":["9549"],"URL":"https:\/\/doi.org\/10.1007\/s10772-018-9549-y","relation":{},"ISSN":["1381-2416","1572-8110"],"issn-type":[{"type":"print","value":"1381-2416"},{"type":"electronic","value":"1572-8110"}],"subject":[],"published":{"date-parts":[[2018,8,28]]},"assertion":[{"value":"7 March 2018","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 July 2018","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 August 2018","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}